Optical Character Recognition |
|
OCR is used for translating images of typewritten or printed text (usually captured by a scanner or camera) into machine-readable form with a standard encoding scheme. Different techniques for OCR have been developed and used under different application scenarios. Some of the applications include conversion of legacy documents to an e-format for document imaging systems, License Plate Reader System for capturing the license number of vehicles. And high speed OCR system for domain specific applications. FeaturesCapability: Our Imaging team has experience to design custom OCR solutions based on the client’s specific requirements. The OCR Engine is independent from font type and size to recognize and can read virtually every kind of printed text. It reads:
It is able to recognize characters, words, text lines, paragraphs or full pages. It's able to split and recognize glued characters and to glue and recognize broken characters, too. To better the performance of OCR engine it pre-process the image with de-skewing and normalization techniques. Accuracy: the OCR engine accuracy is 100% when the print and image quality are good. Even if the image quality is medium, the error rate is usually very low. Speed: 200 / 600 CPS, depending on cpu speed. Input: Color, gray scale or bi tonal images with a 200 DPI or greater resolution can be used as input. Better performances are obtained using gray scale image with 300 DPI resolution since the ocr engine works natively in gray scale. Output: the output includes the ASCII or UNICODE code, the confidence level, Platform: the OCR Engine supports Linux and Windows platforms.
ApplicationsThe OCR Engine finds useful application in the following areas:-
|